RSDet++: Point-Based Modulated Loss for More Accurate Rotated Object Detection
Wen Qian, Xue Yang, Silong Peng, Xiujuan Zhang, Junchi Yan
Abstract
We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration. We introduce a novel modulated rotation loss to alleviate the problem and a rotation sensitivity detection network (RSDet) which consists of an eight-param single-stage rotated object detector and the modulated rotation loss. Our proposed RSDet has several advantages: 1) it reformulates the rotated object detection problem as predicting the corners of objects while most previous methods employ a five-param-based regression method with different measurement units. 2) modulated rotation loss achieves consistent improvement on both five-param and eight-param rotated object detection methods by solving the discontinuity of loss. To further improve the accuracy of our method on objects smaller than 10 pixels, we introduce a novel RSDet++ which consists of a point-based anchor-free rotated object detector and a modulated rotation loss. Extensive experiments demonstrate the effectiveness of both RSDet and RSDet++, which achieve competitive results on rotated object detection in the challenging benchmarks DOTA-v1.0, DOTA-v1.5, and DOTA-v2.0. We hope the proposed method can provide a new perspective for designing algorithms to solve rotated object detection and pay more attention to tiny objects. The codes and models are available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/yangxue0827/RotationDetection</uri> .